Triple
T91379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper New York Bay |
E1835
|
entity |
| Predicate | hasWaterType |
P851
|
FINISHED |
| Object | brackish water |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: brackish water | Statement: [Upper New York Bay, hasWaterType, brackish water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWaterType Context triple: [Upper New York Bay, hasWaterType, brackish water]
-
A.
waterType
chosen
Indicates the specific kind or category of water associated with an entity (e.g., fresh, salt, brackish).
-
B.
hasHydrosphere
Indicates that an entity possesses or is characterized by a surrounding layer or system of water, such as oceans, seas, lakes, or other bodies of liquid water.
-
C.
waterRequirement
Indicates the amount or conditions of water needed for an entity to grow, function, or be maintained properly.
-
D.
waterbodyType
Indicates the classification of a water body according to its type (e.g., river, lake, ocean, etc.).
-
E.
hasWaterQualityHistory
Indicates that an entity is associated with a record or series of records describing changes or measurements of its water quality over time.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a2512ef600819084d3c627f0d534f4 |
completed | Feb. 28, 2026, 2:21 a.m. |
| PD | Predicate disambiguation | batch_69a24eb9a5ac8190b1d1300e8c4e3606 |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.